Browse Items (1473 total)
Sort by:
-
Fuzzy Rule-Based Multimodal Health Monitoring System Leveraging Machine Learning Techniques Using Eeg Datasets For Human Emotion And Psychological Disorders
In recent decades, machine learning and data analysis have become increasingly important in mental health for diagnosing and treating psychological disorders. One area of particular interest is the use of electroencephalography (EEG) brainwave data to classify emotional states and predict psychological disorders. This study proposed a data fusion to enhance the precision of emotion recognition. A feature selection strategy using data fusion techniques was implemented, along with a multi-layer Stacking Classifier combining various algorithms such as support vector classifier, Random Forest, multilayer perceptron, and Nu-support vector classifiers. Features were selected based on Linear Regression-based correlation coefficient scores, resulting in a dataset with 39% of the original 2548 features. This framework achieved a high precision of 98.75% in identifying emotions. The study also focused on negative emotional states for recognizing psychological disorders. A Genetic Algorithm (GA) was used for feature selection, and k-means clustering organized the data. The dataset included 707 trials and 2542 unlabeled features. Resampling techniques ensured a balanced representation of emotional states, and GASearchCV optimized Gradient Boosting classifier hyperparameters. The Elbow Method determined the optimal number of k-Means clusters, and resampling addressed class imbalance. GA parameters and gradient- boosting hyperparameters were empirically determined. ROC curves and classification reports evaluated performance, resulting in a high accuracy of 97.21% in predicting psychological disorders. The proposed system employed fuzzy logic to calculate a health score that combines the outputs of the emotional and psychological disorder monitoring models for a multimodal health monitoring system. This approach provides a more comprehensive assessment of an individual's overall mental health status. The findings suggest that the system achieved high efficiency in predicting emotions, showcasing comprehensive progress in EEG-based emotion analysis and disorder diagnosis. These advancements have potential implications for mental health monitoring and treatment, particularly with the integration of the PHQ-9 Scale and fuzzy logic. -
-
Marketing of malayalam films through new media /
The research studies the marketing strategies used by Malayalam films through New Media. In this research new media includes Facebook, Twitter, YouTube, Whatsapp and instagram. For the past four years there is a new shift in the marketing of Malayalam films. More and more film makers are depending on new media for the marketing of Malayalam films. Through this research the researcher studies the current trends in the new media marketing of Malayalam films. -
Learning foreign languages: A comparative analysis of online learning process vs. traditional educational processes /
Internet has pervaded every aspect of the life of the modern person today in the contemporary world. The fact that the education sector is undergoing vast amount of change in terms of the digital revolution via the internet medium is exemplary of the powerful aspect of the internet medium. This is also the case with the practice of foreign languages by many people, especially the urban educated youth. -
-
Marketing strategies adopted by 5 Bangalore based start-ups /
Marketing strategies allow the organizations to take up the best opportunities available within the limited resources and thus help in maximizing the sale rate and giving a tough sustainable competition. It is a planning process to achieve certain goals, missions and set benchmarks with the help of promotional activities. Marketing helps to generate awareness among the consumers about the product or service and the company which again accelerates the demand among the customers and sales leads. -
Dynamics of Newtonian Fluids and Nanofluids in Various Geometries
In this thesis, the boundary-layer flows of Newtonian fluids in different geometries newlineprimarily, a horizontal surface and a vertical surface. To account for the imperfections arising in realistic scenarios, we have considered a horizontal surface with undulations and a vertical surface with a non-uniform temperature distribution. Additionally, it is wellknown that to meet the cooling rate requirements in the industry, the thermal performance of ordinary heat transfer fluids is not suitable. The concept of insertion of nanometresized metallic particles in the fluid leads to an increase in the thermal conductivity of the newlineordinary base liquids. Therefore, to fully comprehend the affect of these nanoparticles on the onset of convection and fluid motions and to assess how the enhanced thermophysical newlineproperties may affect the heat transfer is another key objective of this research. newlineA Comparative Study of Thermo-convective Flows of a Newtonian Fluid over Three newlineHorizontal Undulated Surfaces in a Porous Medium In the first problem of this thesis, elaborated in Chapter 5, a comparison has been presented between the results of three thermoconvective flows of a Newtonian fluid over uniformly heated, undulated horizontal surfaces in a porous medium against the background of the results of a flat plate. The undulations are assumed to have sinusoidal, sawtooth, and triangular waveforms. At large surface amplitudes, secondary flow is observed in the cases newlineof sinusoidal and triangular waveforms, but not in the cases of a sawtooth surface and a newlineflat plate. The variation of the mean Nusselt number and mean skin friction with surface newlineamplitude and the Rayleigh number indicate that heat transfer and viscous friction at the boundary increase with individual and collective increases in the values of the amplitude and the Rayleigh number. The heat transfer and skin friction by the flat surface are much less than that of all three undulated surfaces. -
-
Large Scale Transportation Data Analysis and Distributed Computational Pipeline for Optimal Metro Passenger Flow Prediction
Transportation has a signifcant impact on controlling traffc around a busy city. Among the transport system, metro rails became the backbone by operating above the traffc. For this reason, we have to take special consideration of the passenger and#64258;ow in the transport system and, by understanding the needs, take timely actions for smooth running. Every metro system stores information about the and#64258;ow of passengers in the form of transactions known as Automatic Fare Collection (AFC) data. For this research, AFC data is taken as the primary newlinesource of information to identify the passenger and#64258;ow within the metro rail platform. Each metro system generates massive data throughout its running period and stores data within the system and considering the size of data generated, the analytic platform has to process them in a distributed paradigm to handle quotBig Dataquot. Artifcial Intelligence (AI) algorithms can derives information, insights, and patterns from this data. The patterns in time series can be identifed from the passenger and#64258;ow data using exploratory analysis. The step is an essential step in data science for understanding the underlying properties of the raw data. The research uses a data platform with a distributed computing and storage mechanism called the JP-DAP. The research leverages the above mentioned platform to extract passenger and#64258;ow data from AFC Ticketing data. After the data engineering, the results of passenger and#64258;ow information underwent further visualization and trend analysis. Based on the facts or patterns identifed from the passenger and#64258;ow information, a decision is taken for forecasting. The initial study will reveal the characteristics of metro usage and practices within the system and fnally derive a solution with machine learning-based forecasting method. The passenger and#64258;ow newlineforecasts based on the above patterns depend on factors like seasonality, trends, cyclicity, location, events, and random effects. -
-
-
Risk Factor Based Stage Advancement Prediction of Cataract Using Deep Learning Techniques
In modern world, Cataract is the predominant causative of blindness. Treatment and detection at the early stage can reduce the number of cataract sufferers and prevent surgery. Two types of images are generally used for cataract related studies- Retinal Images an Slit lamp Images. The quality of Retinal images is selected by utilizing the hybrid naturalness image quality evaluator (hybrid NIQE-PIQE) approach. Here, the raw input image quality score is and Deep newlinelearning convolutional neural network (DCNN) categorizes the images based on quality newlinescore. Then the selected quality images are again pre-processed to remove the noise present in the images. The individual green channel (G-channel) is extracted for noise filtering. Moreover, hybrid modified histogram equalization and homomorphic filtering (Hybrid GMHE-HF) is utilized for enhanced noise filtering. The Slit lamp image quality selection is done using Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) model. Further a new algorithm Normalization based Contrast limited adaptive histogram equalization (NCLAHE) is used for image enhancement. Images are pre-processed utilizing the wiener filtering (WF) with Convolutional neural network (CNN) with adaptive atom search optimization (CNN-AASO) for removing the noise. Further, the denoised image is enhanced by Gaussian mixture based contrast enhancement (GMCE) for contrast enhancement. The cataract detection and classification is performed using two phases. In phase I, the cataract is detected using Deep Optimized Convolutional Recurrent Network_Improved Aquila Optimization (Deep OCRN_IAO) model. Phase II uses slit lamp images and detects the type and grade of cataracts through proposed Batch Equivalence ResNet-101 (BE_ResNet101) model.This work also proposes the risk factors for cataracts and classify the cataracts risk using deep learning models. The dataset is pre-processed by missing values and the string values are converted into numeric values. -
Efficient data mining techniques for medical data
Healthy decision making for the well being is a challenge in the current era with abundant information everywhere. Data mining, machine newlinelearning and computational statistics are the leading fields of study that are supporting the empowered individual to take valuable decisions to optimize the outcome of any working domain. High demand for data newlinehandling exists in healthcare, as the rate of increase in patients is proportional to the rate of population growth and life style changes. Techniques for early diagnosis and prognosis prediction of diseases are the need of the hour to provide better treatment for the human community. Data mining techniques are a boon for building a quality and newlineefficient model for health prediction applications. As cancer explodes everywhere in recent years, the data sets from cancer newlineregistries have been focused as the medical data in this research. The main aim of thesis is to build a constructive and efficient classifier model for cancer prognosis prediction. Most of the existing system develops a diagnosis prediction models from the screening or survey data, as the data newlineset is widely available and are easy to collect due the insensitive nature of newlinethe factors involved in such research. Whereas the prognosis prediction requires a sensitive details of the patients those who are under treatment for a diagnosed disease. Hospitals and the community registries newlinemaintained by the government are the main source for data collection. Well maintained electronic hospital records with histopathology information is not public in India for the researchers. Hence cancer data newlinefrom a US based open access data center has been used in this research for all experimentation. This research work is a progressive model that gradually improves the newlineprediction accuracy by selecting appropriate data mining techniques in each phase. -
-
-
A Study on Upper Domatic Number and Its Variants in Graphs
For a graph G = (V, E), a vertex partition and#8673; = {V1, V2, . . . , Vk} is an upper domatic partition if Vi dominates Vj or Vj dominates Vi or both, for every Vi, Vj 2 and#8673;, whenever i 6= j. The upper domatic number D(G) is the maximum order of an upper domatic partition of G. This thesis consists of studies on upper domatic number and its variants in graphs. The bounds of D(G) in terms of order, size, !(G) and #(G) are established. The class of graphs with equal upper domatic newlinenumber and clique number is characterised. The relation between upper domatic number and minimum degree of the graph is explored. The case when the upper domatic number and domatic number are equal is investigated and the graphs for which D(G) and the domatic number d(G) coincide are characterised. Apart from the relation between the D(G) and other graph parameters, the upper domatic number of some special classes of graphs including unicyclic graphs, complement of cycles and powers of graphs is determined. Transitivity, Tr(G), a variant of upper domatic number is defined as the maximum number of sets in a vertex partition {V1, V2, . . . , Vk} such that Vi dominates Vj where 1 i lt j k. The results from the study on this concept include characterisation of graphs with transitivity at least k, exact values of transitivity of few classes of graphs, few upper bounds of transitivity of graphs, the transitivity of trees and an algorithm to determine the same. Along with this, the concept of total upper domatic number is introduced as a new variant of upper domatic number. The total upper domatic number is the maximum order of a total upper domatic partition of G which is an upper domatic partition such that the graph induced by each partite set does not contain any vertex of degree zero. Basic properties and bounds of upper domatic number in terms of order and maximum degree are discussed. Further, the total upper domatic number of some special classes of graphs is determined. -
Destination Resilience and Smart Tourism Ecosystem : A Destination Management Framework for Competitiveness
Over the past many decades, the travel and tourism industry has been at the forefront of adapting to new changes and accepting the latest technologies. Today's travelers are sophisticated and knowledgeable, as they have all the information available to them easily, which contributes to fast and quick decision making. The world is gradually changing into a much more intelligent and advanced platform that makes it possible to employ techniques like augmented reality, virtual reality, and artificial intelligence. This has proven to be very successful in a variety of fields, including education, healthcare, marketing, and communication. The current study focuses on incorporating smart tourism strategies to build a sustainable ecosystem at destinations, which enhances the competitiveness of the destination and makes it easier for value co- creation among the different stakeholders. Research suggests that although industry-led and government-initiated projects seem to prioritize the use of smart applications in destinations in theory, practical implementation appears to lag behind. Less research has been done in India on gamification, smart wearable technology at travel destinations, and the practical application of AR and VR tools. The study revolves around the South Indian State of Kerala, which has been a pioneer in tourism promotion in the country. In addition to proposing a framework for destination management and tourism competitiveness with smart tourism applications, this study aims to investigate the practical implications of smart tourism tools and technologies at destinations. To shed more light on the findings, a mixed methodology approach is used to analyze the data using a mix of quantitative and qualitative methods. The study's conclusions have significant ramifications for destination management, strategic planning, and the application of smart technologies at travel locations. -
Study of effect of modulations on the onset of rayleigh benard convection in a couple stress fluid
In this thesis we study the linear and non-linear analyses of Rayleigh-Benard convection in a couple stress fluid. The effect of rotational modulation, temperature modulation and gravity modulation in the presence of external constraints like magnetic field and electric field are studied. The problems investigated in this thesis throw light on externally controlled convection in a couple stress fluid. The problems investigated in this thesis have possible applications in geophysics, astrophysics, oceanography engineering and experiment/ space situations with g-jitter connected with gravity simulation studies. with this motivation, we investigate in this thesis four problems and, their summary is given below one by one. (i)Linear and non-liner analyses of rotational modulation on Rayleigh-Benard convection in a couple stress fluid. The linear and non-linear analyses of Rayleigh-Benard convection in a couple stress fluid with rotational modulation is studied. The linear and non-linear analyses are, respectively based on normal mode technique and truncated representation of fourier series. The expression for Rayleigh number and correction Rayleigh number are obtained using regular perturbation method in the case of liner theory. The resulting no-autonomous lorenz model obtained in no-linear analysis is solved numerically using the Runge-Kutta-Fehlberg45 method to quantify the heat transport. The effect of rotational modulation is shown to be stabilizing there by leading to a situation of reduced heat transfer. The problem suggests an elegant method of controlling internal convection.(ii) Linear and non-linear analyses of gravity modulation on Rayleigh-Benard convection in a weakly electrically conducting couple strss fluid.The effect of time-periodic body force on the onset of Rayleigh-Benard convection in weak electrically conducting couple stress fluid is investigated. The stability of the horizontal fluid layer heated from below is examined by assuming time periodic body acceleration. -
Synthesis, Process Parameter Control and Performance of Nano Ceramic Coatings for Diesel Engine Applications
Ceramics are non-metallic inorganic solids which are used in various forms (bulk and newlinecoatings) and environments (low and high temperature) to provide protection from newlinethermal, wear or chemical attack. Due to their high melting point, compressive newlinestrength, oxidation and corrosion resistant properties, ceramics are strong, hard, newlinebrittle and harsh environment resistant. Ceramic coatings are generally applied on newlinemetal components to either enhance their life or augment the performance of the devices they are mounted on. Furthermore, coatings being thin (few small units to hundreds of microns); they do not demand significant alteration in component design. Among the many types of coatings used in engineering applications, Thermal Barrier Coatings (TBC) and wear resistant coatings (WRC) are used to protect metallic components from thermal and mechanical damages respectively. 6 to 8%Yttria stabilized zirconia (6-8% Y2O3-ZrO2), generally designated as 8YSZ has been newlineextensively used as TBC and alpha alumina (and#945;-Al2O3) find applications as WRC. 250 to 300m thick micron grained TBC, with grain sizes typically up to 20 m or even higher are well known to thermally insulate diesel engine combustion chamber to provide enhanced fuel efficiency characteristics. 8YSZ and and#945;-Al2O3 coatings also find use in power plants, textiles, automotive and aero-space industries etc. to provide benefits like improved product quality and energy efficiency, extended wear life, reduced maintenance cycles and costs etc. Among ceramic coatings, nanostructured coatings have received further interest because of their extraordinary properties including enhanced hardness, strength, ductility, and toughness when compared with coatings with micron grained newlinemicrostructure. Nanostructured zirconia is also expected to serve as advanced TBC in newlineengine applications, although information on its feasibility and the technology is mostly classified. -
Effect of magnetic field on the onset of Rayleigh-Benard convection in a micropolar fluid with internal heat generation
The effects of through flow, internal heat generation and magnetic field on the onset of Rayleigh-Benard convection in electrically conducting Micropolar fluid are studied using the Galerkin technique. The eigenvalue is obtained for rigid-free velocity boundary combinations with isothermal and adiabatic on the spin-vanishing boundaries. A linear stability analysis is performed. The influence of various parameters on the onset of convection has been analyzed. The microrotation is assumed to vanish at the boundaries. A linear stability analysis is performed. The influence of various parameters on the onset of convection has been analyzed and their comparative influence on onset is discussed. The problem suggests an elegant method of external control of internal convection.